Estimating Micro-Level On-Road Vehicle Emissions Using the K-Means Clustering Method with GPS Big Data

Abstract

Due to the advanced spatial data collection technologies, the locations of vehicles on roads are now being collected nationwide, so there is a demand for applying a micro-level emission calculation methods to estimate regional and national emissions. However, it is difficult to apply this method due to the low data collection rate and the complicated calculation procedure. To solve these problems, this study proposes a vehicle trajectory extraction method for estimating micro-level vehicle emissions using massive GPS data. We extracted vehicle trajectories from the GPS data to estimate the emission factors for each link at a specific time period. Vehicle trajectory data was divided into several groups through a k-means clustering method, in which the ratios of each operating mode were used as variables for clustering similar vehicle trajectories. The results showed that the proposed method has an acceptable accuracy in estimating emissions. Furthermore, it was also confirmed that the estimated emission factors appropriately reflected the driving characteristics of links. If the proposed method were utilized to update the link-based micro-level emission factors using continuously accumulated trajectory data for the road network, it would be possible to efficiently calculate the regional- or national-level emissions only using traffic volume.